GAN-RXA: A Practical Scalable Solution to Receiver-Agnostic Transmitter Fingerprinting

TL;DR

This paper introduces a scalable two-stage supervised learning framework, RXA, for receiver-agnostic transmitter fingerprinting, significantly improving identification accuracy across different receivers using deep learning techniques.

Contribution

It proposes a novel receiver calibration method with deep learning approaches, including GAN-RXA, to enhance transmitter fingerprinting robustness against receiver impairments.

Findings

Improves classification accuracy by 19.5% across receivers.

Enhances outlier detection ROC AUC by 12.0%.

GAN-RXA further boosts accuracy and ROC AUC.

Abstract

Radio frequency fingerprinting has been proposed for device identification. However, experimental studies also demonstrated its sensitivity to deployment changes. Recent works have addressed channel impacts by developing robust algorithms accounting for time and location variability, but the impacts of receiver impairments on transmitter fingerprints are yet to be solved. In this work, we investigate the receiver-agnostic transmitter fingerprinting problem, and propose a novel two-stage supervised learning framework (RXA) to address it. In the first stage, our approach calibrates a receiver-agnostic transmitter feature-extractor. We also propose two deep-learning approaches (SD-RXA and GAN-RXA) in this first stage to improve the receiver-agnostic property of the RXA framework. In the second stage, the calibrated feature-extractor is utilized to train a transmitter classifier with only one receiver. We evaluate the proposed approaches on the transmitter identification problem using a large-scale WiFi dataset. We show that when a trained transmitter-classifier is deployed on new receivers, the RXA framework can improve the classification accuracy by 19.5%, and the outlier detection ROC AUC by 12.0% compared to a naive approach without calibration. Moreover, GAN-RXA can further increase the closed-set classification accuracy by 5.0%, and the outlier detection ROC AUC by 12.5% compared to the RXA approach.